© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 6-RES-JB
    11. 5820
    Prev
    Next
    INDEX
    Explanations

    content related to starting a business or creating opportunities

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.6.hook_resid_post_16384_anthropic_fast_lr
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    HuggingFaceFW/fineweb
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    50
    +0.23
    1.0%
    689
    +0.10
    0.4%
    1013
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    562
    +0.23
    0.04
    353
    +0.10
    0.04
    1392
    +0.09
    0.04
    Negative Logits
    <bos>
    -2.76
    ,
    -0.74
     ProtoMessage
    -0.72
    pop
    -0.70
     across
    -0.70
    .
    -0.69
    ;
    -0.68
    cshtml
    -0.68
     pop
    -0.67
     nh
    -0.66
    POSITIVE LOGITS
     increa
    2.16
     affor
    2.13
     impra
    1.99
     unwarran
    1.95
     napoli
    1.95
     ibiza
    1.95
     michelin
    1.94
     lidl
    1.92
     stockholm
    1.90
     Juf
    1.90
    Activations Density 0.587%

    No Known Activations